Claude Opus 4.8 Costs 44 Times More Than DeepSeek V4 Pro, Artificial Analysis Latest Evaluation Reveals

According to Artificial Analysis, in the latest AI evaluation, Claude Opus 4.8 scored 56 points with a per-task cost of $1.78, while DeepSeek V4 Pro scored 44 points at just $0.04 per task—making Claude 44 times more expensive. The evaluation revised its benchmarks to assess real-world capabilities including planning, tool usage, and complex task execution, replacing simpler multiple-choice tests. Claude Opus 4.8 led available models, followed by GPT-5.5 with 55 points. Other domestic models performed competitively, with MiniMax M3 also reaching 44 points and Kimi K2.6 at 43 points.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments